swarm: named scheduled prompts for one or more agents, fired in each agent
swarm-controller keeps every scheduled prompt (id, name, agents, body,
anchor, interval, paused) as one document under one key of a new
`schedule-definitions` KV bucket, so each change is a single
compare-and-set and a prompt exists for all of its agents or none. It
writes each agent's key of a new `agent-schedules` bucket as the prompts
naming that agent, without names or other agents, after every change and
on a one-minute reconcile pass. It is the only writer of both, behind
GET/POST /api/schedules and PATCH/DELETE /api/schedules/{id}.
`swarmctl schedule add|list|edit|pause|resume|rm` drives those routes over
the controller socket.
An agent's own queue credential is granted one more subject, the direct
get of its own key in `agent-schedules`. A KV watch is not granted: its
consumer create subject carries no key, so it would cover every agent's.
hive-agent's new schedule ticker reads that key every 10 seconds and fires
due slots as the same `schedule:<id>` todo hive-c0re's worker pushes. Fire
times are anchor + k*interval; the last fired slot per schedule id is kept
in the state db, so a body edit or list refresh never moves or refires a
slot, downtime fires the latest missed slot once, a restart refires
nothing, a one-shot fires once, and paused slots are skipped.
Refs #4914
This commit is contained in:
parent
84c89de71c
commit
a0b1846006
24 changed files with 2617 additions and 19 deletions
416
swarmctl/src/schedule.rs
Normal file
416
swarmctl/src/schedule.rs
Normal file
|
|
@ -0,0 +1,416 @@
|
|||
//! `swarmctl schedule` — the operator's scheduled prompts, through
|
||||
//! swarm-controller's `/api/schedules` routes.
|
||||
//!
|
||||
//! Each verb waits for the controller's answer, which is the list or the
|
||||
//! schedule as stored. Each agent the schedule names picks a change up on its
|
||||
//! next read of its schedule key and fires in its own container.
|
||||
//!
|
||||
//! The shapes below mirror the controller's own `ScheduleView` and request
|
||||
//! bodies, for the reason [`crate::agent`]'s module doc gives.
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use anyhow::{Context as _, Result, bail};
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::agent::{parse_ident, send};
|
||||
|
||||
/// One schedule as the controller shows it.
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct ScheduleView {
|
||||
id: String,
|
||||
name: String,
|
||||
agents: Vec<String>,
|
||||
body: String,
|
||||
anchor_unix: i64,
|
||||
interval_seconds: Option<u64>,
|
||||
paused: bool,
|
||||
next_fire_unix: Option<i64>,
|
||||
}
|
||||
|
||||
/// Body of `POST /api/schedules`.
|
||||
#[derive(Serialize)]
|
||||
struct AddRequest<'a> {
|
||||
name: &'a str,
|
||||
agents: Vec<String>,
|
||||
body: &'a str,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
anchor_unix: Option<i64>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
interval_seconds: Option<u64>,
|
||||
paused: bool,
|
||||
}
|
||||
|
||||
/// Body of `PATCH /api/schedules/{id}`. An absent field is left as it is.
|
||||
#[derive(Default, Serialize)]
|
||||
pub(crate) struct EditRequest {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
name: Option<String>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
body: Option<String>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
anchor_unix: Option<i64>,
|
||||
#[serde(skip_serializing_if = "IntervalEdit::is_keep")]
|
||||
interval_seconds: IntervalEdit,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
paused: Option<bool>,
|
||||
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||
add_agents: Vec<String>,
|
||||
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||
remove_agents: Vec<String>,
|
||||
}
|
||||
|
||||
/// What an edit does to the interval. `Set(None)` is sent as `null`, which
|
||||
/// makes a one-shot; `Keep` is not sent at all.
|
||||
#[derive(Clone, Copy, Default)]
|
||||
enum IntervalEdit {
|
||||
#[default]
|
||||
Keep,
|
||||
Set(Option<u64>),
|
||||
}
|
||||
|
||||
impl IntervalEdit {
|
||||
fn is_keep(&self) -> bool {
|
||||
matches!(self, Self::Keep)
|
||||
}
|
||||
}
|
||||
|
||||
impl Serialize for IntervalEdit {
|
||||
fn serialize<S: serde::Serializer>(&self, s: S) -> Result<S::Ok, S::Error> {
|
||||
match self {
|
||||
Self::Keep | Self::Set(None) => s.serialize_none(),
|
||||
Self::Set(Some(seconds)) => s.serialize_u64(*seconds),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// What `schedule edit` was asked to change.
|
||||
pub(crate) struct EditFlags<'a> {
|
||||
pub name: Option<String>,
|
||||
pub body: Option<String>,
|
||||
pub at: Option<&'a str>,
|
||||
pub every: Option<&'a str>,
|
||||
pub once: bool,
|
||||
pub add_agents: Vec<String>,
|
||||
pub remove_agents: Vec<String>,
|
||||
}
|
||||
|
||||
impl EditRequest {
|
||||
/// The edit `schedule edit` asks for. `once` and `every` are exclusive
|
||||
/// in the CLI, so at most one of them is set here.
|
||||
pub(crate) fn new(flags: EditFlags<'_>) -> Result<Self> {
|
||||
let interval_seconds = match (flags.every, flags.once) {
|
||||
(Some(every), _) => IntervalEdit::Set(Some(parse_every(every)?)),
|
||||
(None, true) => IntervalEdit::Set(None),
|
||||
(None, false) => IntervalEdit::Keep,
|
||||
};
|
||||
let edit = Self {
|
||||
name: flags.name,
|
||||
body: flags.body,
|
||||
anchor_unix: flags.at.map(parse_at).transpose()?,
|
||||
interval_seconds,
|
||||
paused: None,
|
||||
add_agents: agents(&flags.add_agents)?,
|
||||
remove_agents: agents(&flags.remove_agents)?,
|
||||
};
|
||||
if edit.name.is_none()
|
||||
&& edit.body.is_none()
|
||||
&& edit.anchor_unix.is_none()
|
||||
&& edit.interval_seconds.is_keep()
|
||||
&& edit.add_agents.is_empty()
|
||||
&& edit.remove_agents.is_empty()
|
||||
{
|
||||
bail!(
|
||||
"nothing to change: pass --name, --body, --at, --every, --once, --add-agent \
|
||||
or --remove-agent"
|
||||
);
|
||||
}
|
||||
Ok(edit)
|
||||
}
|
||||
|
||||
fn paused(paused: bool) -> Self {
|
||||
Self {
|
||||
paused: Some(paused),
|
||||
..Self::default()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn agents(names: &[String]) -> Result<Vec<String>> {
|
||||
names.iter().map(|n| parse_ident(n, "agent name")).collect()
|
||||
}
|
||||
|
||||
fn runtime() -> Result<tokio::runtime::Runtime> {
|
||||
tokio::runtime::Builder::new_current_thread()
|
||||
.enable_io()
|
||||
.build()
|
||||
.context("starting a tokio runtime for the controller request")
|
||||
}
|
||||
|
||||
const COLLECTION: &str = "/api/schedules";
|
||||
|
||||
/// The schedule's path. The id is checked like an agent name, which every id
|
||||
/// the controller mints satisfies, so it cannot reshape the URI.
|
||||
fn member(id: &str) -> Result<String> {
|
||||
let id = parse_ident(id, "schedule id")?;
|
||||
Ok(format!("{COLLECTION}/{id}"))
|
||||
}
|
||||
|
||||
/// What `schedule add` was asked for.
|
||||
pub(crate) struct AddFlags<'a> {
|
||||
pub name: &'a str,
|
||||
pub agents: &'a [String],
|
||||
pub body: &'a str,
|
||||
pub at: Option<&'a str>,
|
||||
pub every: Option<&'a str>,
|
||||
pub paused: bool,
|
||||
}
|
||||
|
||||
/// Run `swarmctl schedule add`.
|
||||
pub(crate) fn add(socket: &Path, flags: &AddFlags<'_>) -> Result<()> {
|
||||
let request = AddRequest {
|
||||
name: flags.name,
|
||||
agents: agents(flags.agents)?,
|
||||
body: flags.body,
|
||||
anchor_unix: flags.at.map(parse_at).transpose()?,
|
||||
interval_seconds: flags.every.map(parse_every).transpose()?,
|
||||
paused: flags.paused,
|
||||
};
|
||||
let added: ScheduleView = runtime()?.block_on(send(
|
||||
socket,
|
||||
hyper::Method::POST,
|
||||
COLLECTION,
|
||||
Some(&request),
|
||||
"schedule-add",
|
||||
))?;
|
||||
println!("added schedule {}", added.id);
|
||||
println!("{}", render(&added));
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Run `swarmctl schedule list`, optionally only the schedules naming `agent`.
|
||||
pub(crate) fn list(socket: &Path, agent: Option<&str>) -> Result<()> {
|
||||
let agent = agent.map(|a| parse_ident(a, "agent name")).transpose()?;
|
||||
let schedules: Vec<ScheduleView> = runtime()?.block_on(send(
|
||||
socket,
|
||||
hyper::Method::GET,
|
||||
COLLECTION,
|
||||
None::<&()>,
|
||||
"schedule-list",
|
||||
))?;
|
||||
let shown: Vec<&ScheduleView> = schedules
|
||||
.iter()
|
||||
.filter(|s| agent.as_ref().is_none_or(|a| s.agents.contains(a)))
|
||||
.collect();
|
||||
if shown.is_empty() {
|
||||
println!("no schedules");
|
||||
}
|
||||
for s in shown {
|
||||
println!("{}", render(s));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Run `swarmctl schedule edit`.
|
||||
pub(crate) fn edit(socket: &Path, id: &str, edit: &EditRequest) -> Result<()> {
|
||||
let edited: ScheduleView = runtime()?.block_on(send(
|
||||
socket,
|
||||
hyper::Method::PATCH,
|
||||
&member(id)?,
|
||||
Some(edit),
|
||||
"schedule-edit",
|
||||
))?;
|
||||
println!("{}", render(&edited));
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Run `swarmctl schedule pause` or `resume`.
|
||||
pub(crate) fn set_paused(socket: &Path, id: &str, paused: bool) -> Result<()> {
|
||||
edit(socket, id, &EditRequest::paused(paused))
|
||||
}
|
||||
|
||||
/// Run `swarmctl schedule rm`.
|
||||
pub(crate) fn remove(socket: &Path, id: &str) -> Result<()> {
|
||||
let uri = member(id)?;
|
||||
runtime()?.block_on(send::<(), ()>(
|
||||
socket,
|
||||
hyper::Method::DELETE,
|
||||
&uri,
|
||||
None,
|
||||
"schedule-rm",
|
||||
))?;
|
||||
println!("removed schedule {id}");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// `--at`: unix seconds, or an RFC 3339 time with its offset.
|
||||
fn parse_at(value: &str) -> Result<i64> {
|
||||
if let Ok(unix) = value.parse::<i64>() {
|
||||
return Ok(unix);
|
||||
}
|
||||
chrono::DateTime::parse_from_rfc3339(value)
|
||||
.map(|t| t.timestamp())
|
||||
.with_context(|| {
|
||||
format!(
|
||||
"--at {value:?} is neither unix seconds nor an RFC 3339 time such as \
|
||||
2026-10-05T09:00:00+02:00"
|
||||
)
|
||||
})
|
||||
}
|
||||
|
||||
/// `--every`: a positive count of seconds, minutes, hours or days, such as
|
||||
/// `90s`, `15m`, `1h` or `7d`. A bare number is seconds.
|
||||
fn parse_every(value: &str) -> Result<u64> {
|
||||
let (digits, unit) = match value.char_indices().last() {
|
||||
Some((i, c)) if c.is_ascii_alphabetic() => (&value[..i], c),
|
||||
_ => (value, 's'),
|
||||
};
|
||||
let scale = match unit {
|
||||
's' => 1,
|
||||
'm' => 60,
|
||||
'h' => 3600,
|
||||
'd' => 86_400,
|
||||
_ => bail!("--every {value:?}: the unit must be s, m, h or d"),
|
||||
};
|
||||
let count: u64 = digits
|
||||
.parse()
|
||||
.with_context(|| format!("--every {value:?} is not a count followed by s, m, h or d"))?;
|
||||
match count.checked_mul(scale) {
|
||||
Some(0) => bail!("--every {value:?} is zero; leave --every out for a one-shot"),
|
||||
Some(seconds) => Ok(seconds),
|
||||
None => bail!("--every {value:?} is too long"),
|
||||
}
|
||||
}
|
||||
|
||||
fn utc(unix: i64) -> String {
|
||||
chrono::DateTime::from_timestamp(unix, 0).map_or_else(
|
||||
|| unix.to_string(),
|
||||
|t| t.format("%Y-%m-%dT%H:%M:%SZ").to_string(),
|
||||
)
|
||||
}
|
||||
|
||||
/// One row per schedule: id, name, cadence, next fire, agents, and the
|
||||
/// body's first line.
|
||||
fn render(s: &ScheduleView) -> String {
|
||||
let cadence = match s.interval_seconds {
|
||||
Some(i) => format!("every {}", every_text(i)),
|
||||
None => "once".to_owned(),
|
||||
};
|
||||
let next = match (s.paused, s.next_fire_unix) {
|
||||
(true, _) => "paused".to_owned(),
|
||||
(false, Some(t)) => format!("next {}", utc(t)),
|
||||
(false, None) => format!("fired at {}", utc(s.anchor_unix)),
|
||||
};
|
||||
let body = s.body.lines().next().unwrap_or_default();
|
||||
format!(
|
||||
"{} {:?} {cadence} from {} {next} agents: {} | {body}",
|
||||
s.id,
|
||||
s.name,
|
||||
utc(s.anchor_unix),
|
||||
s.agents.join(", ")
|
||||
)
|
||||
}
|
||||
|
||||
fn every_text(seconds: u64) -> String {
|
||||
for (unit, scale) in [("d", 86_400), ("h", 3600), ("m", 60)] {
|
||||
if seconds.is_multiple_of(scale) {
|
||||
return format!("{}{unit}", seconds / scale);
|
||||
}
|
||||
}
|
||||
format!("{seconds}s")
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn flags() -> EditFlags<'static> {
|
||||
EditFlags {
|
||||
name: None,
|
||||
body: None,
|
||||
at: None,
|
||||
every: None,
|
||||
once: false,
|
||||
add_agents: Vec::new(),
|
||||
remove_agents: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn every_takes_a_count_and_a_unit() {
|
||||
assert_eq!(parse_every("90").unwrap(), 90);
|
||||
assert_eq!(parse_every("90s").unwrap(), 90);
|
||||
assert_eq!(parse_every("15m").unwrap(), 900);
|
||||
assert_eq!(parse_every("1h").unwrap(), 3600);
|
||||
assert_eq!(parse_every("7d").unwrap(), 604_800);
|
||||
assert!(parse_every("0h").is_err());
|
||||
assert!(parse_every("1w").is_err());
|
||||
assert!(parse_every("h").is_err());
|
||||
assert!(parse_every("").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn at_takes_unix_seconds_or_rfc3339() {
|
||||
assert_eq!(parse_at("1700000000").unwrap(), 1_700_000_000);
|
||||
assert_eq!(parse_at("1970-01-01T01:00:00+01:00").unwrap(), 0);
|
||||
assert!(parse_at("tomorrow").is_err());
|
||||
}
|
||||
|
||||
/// The edit body says exactly what the flags changed: a `--once` sends an
|
||||
/// explicit `null` interval, and an unset flag sends nothing.
|
||||
#[test]
|
||||
fn an_edit_sends_only_what_was_asked() {
|
||||
let body = |e: &EditRequest| serde_json::to_string(e).unwrap();
|
||||
let e = EditRequest::new(EditFlags {
|
||||
name: Some("hi".to_owned()),
|
||||
..flags()
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(body(&e), r#"{"name":"hi"}"#);
|
||||
let e = EditRequest::new(EditFlags {
|
||||
once: true,
|
||||
..flags()
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(body(&e), r#"{"interval_seconds":null}"#);
|
||||
let e = EditRequest::new(EditFlags {
|
||||
at: Some("5"),
|
||||
every: Some("1m"),
|
||||
add_agents: vec!["iris".to_owned()],
|
||||
remove_agents: vec!["atlas".to_owned()],
|
||||
..flags()
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
body(&e),
|
||||
r#"{"anchor_unix":5,"interval_seconds":60,"add_agents":["iris"],"remove_agents":["atlas"]}"#
|
||||
);
|
||||
assert_eq!(body(&EditRequest::paused(true)), r#"{"paused":true}"#);
|
||||
assert!(EditRequest::new(flags()).is_err());
|
||||
assert!(
|
||||
EditRequest::new(EditFlags {
|
||||
add_agents: vec!["Not An Ident".to_owned()],
|
||||
..flags()
|
||||
})
|
||||
.is_err()
|
||||
);
|
||||
}
|
||||
|
||||
/// The controller's list item, as the wire shape documents it, decodes
|
||||
/// and renders as one row naming every agent.
|
||||
#[test]
|
||||
fn a_listed_schedule_renders_as_one_row() {
|
||||
let s: ScheduleView = serde_json::from_str(
|
||||
r#"{"id":"abc","name":"standup","agents":["atlas","iris"],"body":"post it\nmore",
|
||||
"anchor_unix":0,"interval_seconds":86400,"paused":false,"next_fire_unix":86400}"#,
|
||||
)
|
||||
.unwrap();
|
||||
let row = render(&s);
|
||||
assert!(!row.contains('\n'), "{row}");
|
||||
assert!(row.contains("\"standup\""), "{row}");
|
||||
assert!(row.contains("every 1d"), "{row}");
|
||||
assert!(row.contains("next 1970-01-02T00:00:00Z"), "{row}");
|
||||
assert!(row.contains("agents: atlas, iris"), "{row}");
|
||||
assert!(row.ends_with("| post it"), "{row}");
|
||||
}
|
||||
}
|
||||
Loading…
Reference in a new issue